Development and external validation of a predictive model for pathological complete response of rectal cancer patients including sequential PET-CT imaging
Development and external validation of a predictive model for pathological complete response of rectal cancer patients including sequential PET-CT imaging
复制标题
DOI：
10.1016/j.radonc.2010.12.002
复制
发表时间：
2011-01-01
影响因子：
5.7
通讯作者：
Lambin, Philippe
中科院分区：
文献类型：
--
作者：
van Stiphout, Ruud G. P. M.;Lammering, Guido;Lambin, Philippe
目的：根据临床和序贯 PET-CT 数据，开发和验证直肠癌放化疗 (CRT) 后病理完全缓解 (pCR) 的准确预测模型和列线图。准确的预测可以实现更个体化的手术方法，包括不太广泛的切除甚至观望政策。方法和材料：从四个不同的机构收集了 953 名患者的基于人群的数据库，并将其分为三组：临床因素（培训：677 名患者，验证：85 名患者）、CRT 前 PET-CT（培训：114 名患者，验证：37 名患者）和 CRT 后 PET-CT（培训：107 名患者）患者，验证：55 名患者）。 pCR 定义为术后病理报告的 ypT0N0。使用线性多元分类模型（支持向量机）对数据进行分析，并使用受试者工作特征（ROC）曲线的曲线下面积（AUC）评估模型的性能。结果：数据集中pCR的发生率在15%至31%之间。基于临床变量的模型（AUC（训练）= 0.61 +/- 0.03，AUC（验证）= 0.69 +/- 0.08）产生以下预测因子：cT 和 cN 分期以及肿瘤长度。添加 CRT 前 PET 数据并没有导致性能显着提高（AUC（训练）= 0.68 +/- 0.08，AUC（验证）= 0.68 +/- 0.10），并显示最大放射性同位素摄取（SUVmax）和肿瘤位置作为额外的预测因子。获得的最佳模型基于 CRT 后 PET 数据的添加（AUC（训练）= 0.83 +/- 0.05，AUC（验证）= 0.86 +/- 0.05），并包括以下预测因子：肿瘤长度、CRT 后 SUVmax 和 SUVmax 的相对变化。该模型的表现明显优于临床模型（p(train) < 0.001，p(validation) = 0.056）。结论：基于临床和序贯PET-CT数据开发的模型和列线图可以准确预测pCR，经前瞻性验证后可作为手术决策支持工具。 (C) 2010 Elsevier Ireland Ltd. 保留所有权利。放射治疗与肿瘤学98（2011）126-133
Purpose: To develop and validate an accurate predictive model and a nomogram for pathologic complete response (pCR) after chemoradiotherapy (CRT) for rectal cancer based on clinical and sequential PET-CT data. Accurate prediction could enable more individualised surgical approaches, including less extensive resection or even a wait-and-see policy.Methods and materials: Population based databases from 953 patients were collected from four different institutes and divided into three groups: clinical factors (training: 677 patients, validation: 85 patients), pre-CRT PET-CT (training: 114 patients, validation: 37 patients) and post-CRT PET-CT (training: 107 patients, validation: 55 patients). A pCR was defined as ypT0N0 reported by pathology after surgery. The data were analysed using a linear multivariate classification model (support vector machine), and the model's performance was evaluated using the area under the curve (AUC) of the receiver operating characteristic (ROC) curve.Results: The occurrence rate of pCR in the datasets was between 15% and 31%. The model based on clinical variables (AUC(train) = 0.61 +/- 0.03, AUC(validation) = 0.69 +/- 0.08) resulted in the following predictors: cT- and cN-stage and tumour length. Addition of pre-CRT PET data did not result in a significantly higher performance (AUC(train) = 0.68 +/- 0.08, AUC(validation) = 0.68 +/- 0.10) and revealed maximal radioactive isotope uptake (SUVmax) and tumour location as extra predictors. The best model achieved was based on the addition of post-CRT PET-data (AUC(train) = 0.83 +/- 0.05, AUC(validation) = 0.86 +/- 0.05) and included the following predictors: tumour length, post-CRT SUVmax and relative change of SUVmax. This model performed significantly better than the clinical model (p(train) < 0.001, p(validation) = 0.056).Conclusions: The model and the nomogram developed based on clinical and sequential PET-CT data can accurately predict pCR, and can be used as a decision support tool for surgery after prospective validation. (C) 2010 Elsevier Ireland Ltd. All rights reserved. Radiotherapy and Oncology 98 (2011) 126-133